© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5533
    Prev
    Next
    INDEX
    Explanations

    C++ code snippets, focusing on array and variable declarations and basic output statements

    oai_token-act-pair · gemini-2.0-flash

    code or numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.85
     تضيفلها
    -0.71
    .")
    -0.65
    #.
    -0.65
    .].
    -0.65
     ujednoznacz
    -0.63
    日閲覧
    -0.63
    ."]
    -0.62
    مصادر
    -0.61
    $
    -0.60
    POSITIVE LOGITS
    ,
    0.48
     Union
    0.44
     AssemblyCulture
    0.44
     HasFactory
    0.42
    getStatusCode
    0.41
    ModelForm
    0.40
    AnchorTagHelper
    0.40
    moveToFirst
    0.40
    cokinetic
    0.39
    oredCriteria
    0.39
    Activations Density 1.918%

    No Known Activations